vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	cmake/common.cmake
#	docs/backend/SYCL.md
#	examples/main/README.md
#	examples/speculative/speculative.cpp
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2025-03-19 19:27:11 +08:00
commit 0c90d2ebcf
58 changed files with 4222 additions and 1537 deletions
Download patch file Download diff file Expand all files Collapse all files

8
examples/server/server.cpp
View file

@ -1872,6 +1872,10 @@ struct server_context {
params_dft.n_gpu_layers = params_base.speculative.n_gpu_layers;
params_dft.n_parallel = 1;
// force F16 KV cache for the draft model for extra performance
params_dft.cache_type_k = GGML_TYPE_F16;
params_dft.cache_type_v = GGML_TYPE_F16;
llama_init_dft = common_init_from_params(params_dft);
model_dft = llama_init_dft.model.get();
@ -1892,10 +1896,6 @@ struct server_context {
cparams_dft = common_context_params_to_llama(params_dft);
cparams_dft.n_batch = n_ctx_dft;
// force F16 KV cache for the draft model for extra performance
cparams_dft.type_k = GGML_TYPE_F16;
cparams_dft.type_v = GGML_TYPE_F16;
// the context is not needed - we will create one for each slot
llama_init_dft.context.reset();
}